add raptor (#11527)

.github/workflows/publish_sub_package.yml

@@ -4,6 +4,7 @@ on:
   push:
     branches:
       - main
+
 env:
   POETRY_VERSION: "1.6.1"
   PYTHON_VERSION: "3.10"

llama-index-packs/llama-index-packs-raptor/.gitignore

@@ -0,0 +1,153 @@
+llama_index/_static
+.DS_Store
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+bin/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+etc/
+include/
+lib/
+lib64/
+parts/
+sdist/
+share/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+.ruff_cache
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+notebooks/
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+pyvenv.cfg
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Jetbrains
+.idea
+modules/
+*.swp
+
+# VsCode
+.vscode
+
+# pipenv
+Pipfile
+Pipfile.lock
+
+# pyright
+pyrightconfig.json

llama-index-packs/llama-index-packs-raptor/BUILD

@@ -0,0 +1,4 @@
+poetry_requirements(
+    name="poetry",
+    module_mapping={"umap-learn": ["umap"], "scikit-learn": ["sklearn"]}
+)

llama-index-packs/llama-index-packs-raptor/Makefile

@@ -0,0 +1,17 @@
+GIT_ROOT ?= $(shell git rev-parse --show-toplevel)
+
+help:	## Show all Makefile targets.
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[33m%-30s\033[0m %s\n", $$1, $$2}'
+
+format:	## Run code autoformatters (black).
+	pre-commit install
+	git ls-files | xargs pre-commit run black --files
+
+lint:	## Run linters: pre-commit (black, ruff, codespell) and mypy
+	pre-commit install && git ls-files | xargs pre-commit run --show-diff-on-failure --files
+
+test:	## Run tests via pytest.
+	pytest tests
+
+watch-docs:	## Build and watch documentation.
+	sphinx-autobuild docs/ docs/_build/html --open-browser --watch $(GIT_ROOT)/llama_index/

llama-index-packs/llama-index-packs-raptor/README.md

@@ -0,0 +1,78 @@
+# Raptor Retriever LlamaPack
+
+This LlamaPack shows how to use an implementation of RAPTOR with llama-index, leveraging the RAPTOR pack.
+
+RAPTOR works by recursively clustering and summarizing clusters in layers for retrieval.
+
+There two retrieval modes:
+
+- tree_traversal -- traversing the tree of clusters, performing top-k at each level in the tree.
+- collapsed -- treat the entire tree as a giant pile of nodes, perform simple top-k.
+
+See [the paper](https://arxiv.org/abs/2401.18059) for full algorithm details.
+
+## CLI Usage
+
+You can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
+
+```bash
+llamaindex-cli download-llamapack RaptorPack --download-dir ./raptor_pack
+```
+
+You can then inspect/modify the files at `./raptor_pack` and use them as a template for your own project.
+
+## Code Usage
+
+You can alternaitvely install the package:
+
+`pip install llama-index-packs-raptor`
+
+Then, you can import and initialize the pack! This will perform clustering and summarization over your data.
+
+```python
+from llama_index.packs.raptor import RaptorPack
+
+pack = RaptorPack(documents, llm=llm, embed_model=embed_model)
+```
+
+The `run()` function is a light wrapper around `retriever.retrieve()`.
+
+```python
+nodes = pack.run(
+    "query",
+    mode="collapsed",  # or tree_traversal
+)
+```
+
+You can also use modules individually.
+
+```python
+# get the retriever
+retriever = pack.retriever
+```
+
+## Persistence
+
+The `RaptorPack` comes with the `RaptorRetriever`, which offers ways of saving/reloading!
+
+If you are using a remote vector-db, just pass it in
+
+```python
+# Pack usage
+pack = RaptorPack(..., vector_store=vector_store)
+
+# RaptorRetriever usage
+retriever = RaptorRetriever(..., vector_store=vector_store)
+```
+
+Then, to re-connect, just pass in the vector store again and an empty list of documents
+
+```python
+# Pack usage
+pack = RaptorPack([], ..., vector_store=vector_store)
+
+# RaptorRetriever usage
+retriever = RaptorRetriever([], ..., vector_store=vector_store)
+```
+
+Check out the [notebook here for complete details!](https://github.com/run-llama/llama_index/blob/main/llama-index-packs/llama-index-packs-raptor/examples/raptor.ipynb).